Intelligent power grid power transformation and distribution station management system based on cloud computing and method thereof

Abstract

The invention discloses an intelligent power grid power transformation and distribution station management system and method based on cloud computing, and relates to the technical field of machine learning, and the method comprises the steps: collecting power data through a plurality of sensors and intelligent devices installed on an intelligent power grid power transformation and distribution station, and carrying out the data preprocessing on an edge computing node; uploading the preprocessed data to a cloud computing platform, and performing credibility analysis on the data by using a Bayesian algorithm; for the data passing the credibility verification, using a support vector machine (SVM) model in combination with a kernel function to identify attack behaviors and classifications; once an attack behavior is identified, a corresponding response mechanism is started immediately, and meanwhile, visual display is performed through an enterprise power operation and maintenance cloud platform. Through a series of technologies, the attack detection precision is improved, the false alarm rate is reduced, and the overall security of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of machine learning, and in particular to a cloud computing-based smart grid substation management system and method thereof. Background Art

[0002] With the rapid development of smart grid technology, the automation and intelligence level of power systems continues to improve, especially in data collection and analysis. Traditional substation management still faces many challenges. At present, most smart grid substation management systems rely on centralized data processing centers, which are susceptible to single point failures and have high data transmission delays, making it difficult to achieve real-time monitoring and rapid response. In addition, the number of attacks on power grid systems is increasing, and traditional methods are insufficient in attack detection and response speed, especially in data credibility verification. Current systems usually use a single statistical method, which is not accurate enough for identifying attack behaviors in complex network environments.

[0003] The limitations of existing technologies in data preprocessing and anomaly detection are particularly prominent, especially when faced with massive amounts of data. How to efficiently screen and evaluate data credibility has become an urgent problem to be solved. Traditional data processing methods often cannot meet real-time requirements, and the accuracy of identifying attack behaviors needs to be improved. In contrast, our invention introduces edge computing nodes for data preprocessing, combines the Bayesian algorithm of the cloud computing platform for data credibility analysis, and uses the support vector machine SVM model combined with the kernel function for attack behavior identification. It can improve the system's response speed and detection accuracy while ensuring data quality. The present invention aims to solve the problems of insufficient data credibility verification and inaccurate attack behavior detection in the prior art, and belongs to the field of smart grid data processing and network security technology. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a cloud computing-based smart grid substation management system and method thereof to solve the problems of data credibility verification and attack behavior identification.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a smart grid substation management method based on cloud computing, which includes collecting power data through various sensors and intelligent devices installed in the smart grid substation, and preprocessing the data on the edge computing node; uploading the preprocessed data to the cloud computing platform, and using the Bayesian algorithm to perform credibility analysis on the data; for data that has passed the credibility verification, using the support vector machine SVM model combined with the kernel function to identify and classify attack behaviors; once the attack behavior is identified, the corresponding response mechanism is immediately initiated, and at the same time, it is visualized through the enterprise power operation and maintenance cloud platform.

[0008] As a preferred solution of the cloud computing-based smart grid substation management method of the present invention, wherein: the power data is collected by various sensors and intelligent devices installed in the smart grid substation, and data preprocessing is performed on the edge computing node. The specific steps are:

[0009] Deploy multifunctional sensor arrays in smart grid substations, including current transformers, voltage transformers, temperature sensors, vibration sensors, and harmonic detectors;

[0010] The sensor collects data at a fixed frequency of once per second;

[0011] After data collection is completed, preprocessing is performed at the edge computing node.

[0012] As a preferred solution of the cloud computing-based smart grid substation management method of the present invention, the pre-processed data is uploaded to the cloud computing platform, and the Bayesian algorithm is used to analyze the credibility of the data. The specific steps are:

[0013] Upload the preprocessed data to the cloud computing platform and store it in distributed files;

[0014] Through the computing power of the cloud computing platform, the Bayesian algorithm is used to perform multi-dimensional analysis of the data and calculate the credibility index. The expression is:

[0015]

[0016] Among them, Z represents the final credibility index, a1 represents the characteristic parameter of current, b1 represents the characteristic parameter of voltage, c1 represents the characteristic parameter of temperature, X represents the temperature value at the current moment, X1 represents the current value at the current moment, X2 represents the historical reference current value, X3 represents the voltage value at the current moment, X4 represents the historical reference voltage value, d1 represents the standardization coefficient of current, e1 represents the standardization coefficient of voltage, and f1 represents the standardization coefficient of temperature.

[0017] As a preferred solution of the intelligent power grid substation management method based on cloud computing according to the present invention, wherein: the judgment of the credibility value means that,

[0018] When the value of Z satisfies -0.1 < Z < 0.1, the data is reliable;

[0019] When the value of Z satisfies Z ≤ -0.1 or Z ≥ 0.1, the data is abnormal.

[0020] As a preferred solution of the intelligent power grid substation management method based on cloud computing according to the present invention, wherein: for the data that passes the credibility verification, the support vector machine SVM model is used in combination with the kernel function to identify attack behaviors and classify them. The specific steps are as follows:

[0021] For the data that passes the credibility verification, the support vector machine SVM model is used for classification and identification. The expression is:

[0022]

[0023] Among them, F(Y) represents the final classification function, n represents the number of features, w i represents the weight of the i-th feature y i of, φ(y i ) is the Gaussian kernel function, ψ(y i ) is the Laplace kernel function, k is the slope parameter in the logarithmic logistic regression model, l is the intercept parameter in the logarithmic logistic regression model, y i represents the value of the i-th feature, b is the bias term value, and i is the index of the feature.

[0024] As a preferred solution of the intelligent power grid substation management method based on cloud computing according to the present invention, wherein: the judgment of the attack behavior category means that,

[0025] When F(Y) > 0.5, it is judged that the data Y belongs to the attack behavior category;

[0026] When F(Y) ≤ 0.5, it is judged that the data Y does not belong to the attack behavior category.

[0027] As a preferred solution of the intelligent power grid substation management method based on cloud computing according to the present invention, wherein: once an attack behavior is identified, the corresponding response mechanism is immediately activated, and at the same time, it is visually displayed through the enterprise power operation and maintenance cloud platform. The specific steps are as follows:

[0028] Once an attack behavior is identified, the power grid substation immediately activates the corresponding response mechanism, including automatically isolating the affected network, isolating the faulty equipment, adjusting the load distribution, sending an alarm notification, recording the event and generating a report, starting the emergency plan, implementing defense measures, and coordinating the response;

[0029] Automatically notify operation and maintenance personnel to take measures and record the operations based on the type and severity of the attack;

[0030] All data and time records are visualized through the enterprise power operation and maintenance platform;

[0031] Operation and maintenance personnel can check the operating status of the power grid system through the operation and maintenance platform.

[0032] In the second aspect, the present invention provides a smart grid substation management system based on cloud computing, including a collection module, an upload module, a credibility module, an identification and classification module, and a response recording module; the collection module is used to collect power data through various sensors and intelligent devices installed in the smart grid substation, and perform data preprocessing on the edge computing node; the credibility module is used to upload the preprocessed data to the cloud computing platform, and use the Bayesian algorithm to perform credibility analysis on the data; the identification and classification module is used to identify and classify attack behaviors for data that has passed credibility verification using a support vector machine SVM model combined with a kernel function; the response recording module is used to immediately activate the corresponding response mechanism once an attack behavior is identified, and at the same time perform visual display through the enterprise power operation and maintenance cloud platform.

[0033] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the cloud computing-based smart grid substation management method as described in the first aspect of the present invention is implemented.

[0034] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the cloud computing-based smart grid substation management method as described in the first aspect of the present invention.

[0035] The beneficial effects of the present invention are as follows: by using the support vector machine (SVM) model in combination with the kernel function to identify attack behaviors and classification, the SVM model uses the kernel function to map data to a high-dimensional space and capture nonlinear relationships. The high-precision classification function of the SVM model enables the system to quickly respond to potential threats and reduce the chances of successful attacks. Once the attack behavior is identified, the system immediately initiates a response mechanism, including isolating the affected network, isolating the faulty equipment, adjusting the load distribution, etc., thereby minimizing the scope of the fault impact and more effectively identifying complex attack patterns, which not only improves the accuracy of attack detection, but also reduces the false alarm rate, thereby ensuring the overall security of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0037] Figure 1 This is a flow chart of the smart grid substation management method based on cloud computing in Example 1.

[0038] Figure 2 This is a flow chart of data collection and preprocessing in Example 1. DETAILED DESCRIPTION

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0041] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0042] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a smart grid substation management method based on cloud computing, comprising the following steps:

[0043] S1. Collect power data through various sensors and intelligent devices installed in smart grid substations, and pre-process the data on edge computing nodes.

[0044] Going a step further, a multifunctional sensor array is deployed in the smart grid substation, including current transformers, voltage transformers, temperature sensors, vibration sensors, and harmonic detectors;

[0045] The sensor collects data at a fixed frequency of once per second;

[0046] Data collection is completed, and preprocessing is carried out at the edge computing node. The Kalman filtering algorithm is used to filter the original data to remove noise interference caused by environmental factors. Then, the Z-Score method is adopted for outlier detection, and any data points exceeding three standard deviations will be regarded as abnormal and marked.

[0047] To ensure data uniformity, all data is converted into structured data packets in JSON format.

[0048] It should be noted that ensuring the data collected from the power system is both accurate and consistent lays a solid foundation for subsequent data analysis, fault detection, system optimization, etc. Through effective data preprocessing, false alarms and missed alarms can be reduced, and the management level and operation efficiency of the entire smart grid can be improved.

[0049] S2. Upload the preprocessed data to the cloud computing platform and use the Bayesian algorithm to analyze the credibility of the data.

[0050] Furthermore, upload the preprocessed data to the cloud computing platform and store it in a distributed file;

[0051] Through the computing power of the cloud computing platform, use the Bayesian algorithm to perform multi-dimensional analysis on the data and calculate the credibility index. The expression is:

[0052]

[0053] Among them, Z represents the final credibility index, a1 represents the characteristic parameter of current, b1 represents the characteristic parameter of voltage, c1 represents the characteristic parameter of temperature, X represents the temperature value at the current moment, X1 represents the current value at the current moment, X2 represents the historical reference current value, X3 represents the voltage value at the current moment, X4 represents the historical reference voltage value, d1 represents the normalization coefficient of current, e1 represents the normalization coefficient of voltage, and f1 represents the normalization coefficient of temperature.

[0054] The judgment of the credibility value means that,

[0055] When the value of Z satisfies -0.1 < Z < 0.1, the data is reliable;

[0056] When the value of Z satisfies Z ≤ -0.1 or Z ≥ 0.1, the data is abnormal.

[0057] It should be noted that the transmission of the preprocessed data from the edge computing node to the cloud computing platform involves the following steps:

[0058] Ensure that the data is encapsulated in JSON format;

[0059] To protect data security, the data is usually encrypted;

[0060] Choose an appropriate communication protocol (such as HTTPS) to ensure secure data transmission;

[0061] Send data to the designated cloud server through the network interface;

[0062] Verify that the data was uploaded successfully and was not lost or corrupted during transmission.

[0063] It should be noted that power system data usually contains key information about the operation of the power grid. If this information is leaked, it may pose a threat to user privacy, business secrets and even national security. Therefore, data encryption can prevent unauthorized access and use.

[0064] Encryption not only protects data from being stolen, but also ensures that data is not tampered with or damaged during transmission; this is particularly important in power systems because data integrity directly affects system stability and reliability;

[0065] Many countries and regions have strict data protection laws and regulations that require the use of encryption technology when transmitting sensitive information; complying with these regulations is not only a legal responsibility, but also a commitment to users;

[0066] Without proper encryption measures during data transmission, hackers can intercept and tamper with data through man-in-the-middle attacks; encryption can effectively prevent such attacks;

[0067] When users know that their data is properly protected, they will be more willing to use the services provided by the system; therefore, strengthening data encryption and transmission security can also help enhance user confidence.

[0068] It should be noted that the specific processing flow of using the Bayesian algorithm to conduct credibility analysis on data on the cloud computing platform includes:

[0069] Receive and store data from edge computing nodes;

[0070] Check the consistency and completeness of the data again. Some preprocessing work may be required, such as filling in missing values.

[0071] Extract features relevant to the analysis and prepare the dataset for Bayesian algorithms;

[0072] Apply Bayesian algorithm to analyze the credibility of data and update the posterior probability based on prior knowledge;

[0073] The credibility index of the data is output based on the results of the Bayesian algorithm.

[0074] It should be noted that this step performs credibility analysis on the pre-processed power data through the cloud computing platform to ensure the accuracy and reliability of the data, thereby supporting the efficient management and safe operation of the power system.

[0075] S3. For data that has passed the credibility verification, the support vector machine (SVM) model is used in combination with the kernel function to identify attack behaviors and classify them.

[0076] Furthermore, for the data that has passed the credibility verification, the support vector machine SVM model is used for classification and recognition, and the expression is:

[0077]

[0078] Among them, F(Y) represents the final classification function, n represents the number of features, that is, the dimension of the feature vector contained in the data Y, and w i represents the i-th feature y i The weight of φ(y i ) is a Gaussian kernel function used to transform the feature y i Mapping to a high-dimensional space, for example, it can be used to capture nonlinear relationships between features, ψ(y i ) is the Laplace kernel function, which is also used to transform the feature y i Mapped to high-dimensional space, it is used to capture another nonlinear relationship between features. k is the slope parameter in the logarithmic logistic regression model, which is used to adjust the steepness of the sigmoid function. It determines the inclination angle of the sigmoid function curve. l is the intercept parameter in the logarithmic logistic regression model, which is used to adjust the position of the sigmoid function. It determines the center position of the sigmoid function curve. i Indicates the value of the i-th feature, which is a feature component in the data Y to be classified and identified, exp(-k·(y i -l)) represents the sigmoid function exp(-k·(y i -l)) is used to convert feature y i Mapped to a value between 0 and 1 to represent the normalized importance of the feature, b is the bias value, which is used to adjust the baseline position of the classification function so that the classification function can better fit the data, and i is the index of the feature.

[0079] For the category judgment of attack behavior, it means,

[0080] When F(Y)>0.5, the data Y is judged to belong to the category of aggressive behavior;

[0081] When F(Y)≤0.5, it is judged that the data Y does not belong to the attack behavior category.

[0082] It should be noted that k is a parameter used to adjust the steepness of the sigmoid function. Simply put, k controls the inclination angle of the sigmoid function curve; a larger k value will make the function curve steeper, which means that for a small change in the input variable, the probability value of the function output will change significantly; therefore, k determines the sensitivity of the model to the data;

[0083] l is a parameter used to adjust the position of the sigmoid function. l determines the center position of the sigmoid function curve, which is the input value when the function reaches half the probability (0.5); in other words, l affects when the function begins to transition from 0 to 1.

[0084] It should be noted that the support vector machine (SVM) model is a supervised learning model, mainly used for classification and regression analysis; its core idea is to find a hyperplane, which is called a "hyperplane" in high-dimensional or multi-dimensional space, which can separate data of different categories as clearly as possible; the construction process of the SVM model is as follows:

[0085] The kernel function is used to map the data in the input space into a higher-dimensional space, so that it is easier to find the boundaries that separate the data in the new space;

[0086] Determine the optimal decision boundary (also called the maximum margin hyperplane) by maximizing the boundary distance;

[0087] By solving a convex optimization problem to find the optimal support vectors, that is, those sample points closest to the decision boundary;

[0088] The classifier is constructed using the support vectors found and the weights corresponding to the support vectors.

[0089] It should be noted that the data verified by credibility is classified by applying the support vector machine (SVM) model combined with the kernel function, especially to identify potential attack behaviors; the purpose of this is to improve the power system's detection capability and response speed to abnormal behaviors, thereby enhancing the security of the system.

[0090] S4. Once the attack behavior is identified, the corresponding response mechanism is immediately activated, and the enterprise power operation and maintenance cloud platform is used for visual display.

[0091] Furthermore, once the attack behavior is identified, the power grid substation immediately initiates the corresponding response mechanism, including automatically isolating the affected network, isolating the faulty equipment, adjusting the load distribution, sending alarm notifications, recording the event and generating reports, initiating emergency plans, implementing defense measures, and coordinating responses;

[0092] Automatically notify operation and maintenance personnel to take measures and record the operations based on the type and severity of the attack;

[0093] All data and time records are visualized through the enterprise power operation and maintenance platform;

[0094] Operation and maintenance personnel can check the operating status of the power grid system through the operation and maintenance platform.

[0095] It should be noted that the design of the response mechanism usually needs to consider the following aspects:

[0096] Once an attack is detected, the system should be able to automatically isolate the affected part to prevent the attack from spreading;

[0097] Shut down or isolate equipment that may fail to prevent it from causing greater impact on the power grid;

[0098] Adjust the load distribution of the power grid according to the current situation to ensure the normal operation of other parts;

[0099] Send alerts to relevant personnel to inform them of the problem and its severity;

[0100] Record the events that occurred and the measures taken, and generate detailed reports for later analysis;

[0101] Take appropriate protective measures according to the preset emergency plan;

[0102] If necessary, coordinate with other departments or agencies to jointly respond to emergencies.

[0103] It should be noted that anomalies are quickly isolated and handled through an automated response mechanism, while the operating status of the power system is monitored and displayed in real time through a visualization platform to ensure the safe and stable operation of the system.

[0104] The present embodiment also provides a cloud computing-based smart grid substation management system, including: a collection module, an upload module, a credibility module, an identification and classification module, and a response recording module; the collection module is used to collect power data through various sensors and intelligent devices installed in the smart grid substation, and perform data preprocessing on the edge computing node; the credibility module is used to upload the preprocessed data to the cloud computing platform, and use the Bayesian algorithm to perform credibility analysis on the data; the identification and classification module is used to identify and classify attack behaviors for data that has passed credibility verification using a support vector machine SVM model combined with a kernel function; the response recording module is used to immediately activate the corresponding response mechanism once an attack behavior is identified, and at the same time perform visual display through the enterprise power operation and maintenance cloud platform.

[0105] This embodiment also provides a computer device, which is suitable for the case of a smart grid substation management method based on cloud computing, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the smart grid substation management method based on cloud computing proposed in the above embodiment.

[0106] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0107] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for managing a smart grid substation based on cloud computing proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0108] In summary, the present invention uses a support vector machine (SVM) model in combination with a kernel function to identify and classify attack behaviors. The SVM model uses a kernel function to map data to a high-dimensional space and capture nonlinear relationships. The high-precision classification function of the SVM model enables the system to quickly respond to potential threats and reduce the chances of successful attacks. Once an attack behavior is identified, the system immediately initiates a response mechanism, including isolating the affected network, isolating faulty equipment, adjusting load distribution, etc., thereby minimizing the scope of the fault impact and more effectively identifying complex attack patterns, which not only improves the accuracy of attack detection, but also reduces the false alarm rate, thereby ensuring the overall security of the system.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A cloud computing-based smart grid substation management method, characterized in that: including collecting power data through a variety of sensors and intelligent devices installed in the intelligent power grid substation and preprocessing the data on the edge computing node; uploading the preprocessed data to the cloud computing platform and using the Bayesian algorithm to analyze the credibility of the data; for the data that passes the credibility verification, using the support vector machine SVM model combined with the kernel function to identify attack behaviors and classify; once an attack behavior is identified, immediately activate the corresponding response mechanism and at the same time conduct visual display through the enterprise power operation and maintenance cloud platform.

2. The cloud computing-based smart grid substation management method according to claim 1, characterized in that: The step of collecting power data through a variety of sensors and intelligent devices installed in the intelligent power grid substation and preprocessing the data on the edge computing node is specifically as follows: deploy a multi-functional sensor array in the intelligent power grid substation, including current transformers, voltage transformers, temperature sensors, vibration sensors and harmonic detectors; the sensors collect data at a fixed frequency of once per second; after the data collection is completed, preprocess it on the edge computing node.

3. The cloud computing-based smart grid substation management method according to claim 2, characterized in that: The step of uploading the preprocessed data to the cloud computing platform and using the Bayesian algorithm to analyze the credibility of the data is specifically as follows: upload the preprocessed data to the cloud computing platform and store it in a distributed file; through the computing power of the cloud computing platform, use the Bayesian algorithm to conduct multi-dimensional analysis on the data and calculate the credibility index. The expression is: where Z represents the final credibility index, a1 represents the characteristic parameter of current, b1 represents the characteristic parameter of voltage, c1 represents the characteristic parameter of temperature, X represents the temperature value at the current moment, X1 represents the current value of current, X2 represents the historical reference current value, X3 represents the voltage value at the current moment, X4 represents the historical reference voltage value, d1 represents the normalization coefficient of current, e1 represents the normalization coefficient of voltage, and f1 represents the normalization coefficient of temperature.

4. The cloud computing-based smart grid substation management method according to claim 3, characterized in that: The judgment of the credibility value refers to: when the value of Z satisfies -0.1 < Z < 0.1, the data is reliable; when the value of Z satisfies Z ≤ -0.1 or Z ≥ 0.1, the data is abnormal.

5. The cloud computing-based smart grid substation management method according to claim 4, characterized in that: The step of using the support vector machine SVM model combined with the kernel function to identify attack behaviors and classify for the data that passes the credibility verification is specifically as follows: for the data that passes the credibility verification, use the support vector machine SVM model for classification and identification. The expression is: Among them, F(Y) represents the final classification function, n represents the number of features, and w i represents the i-th feature y i The weight of φ(y i ) is the Gaussian kernel function, ψ(y i ) is the Laplace kernel function, k is the slope parameter in the logistic regression model, l is the intercept parameter in the logistic regression model, and y i represents the value of the i-th feature, b is the bias value, and i is the index of the feature.

6. The cloud computing-based smart grid substation management method according to claim 5, characterized in that: The judgment of the attack behavior category refers to: when F(Y) > 0.5, it is judged that the data Y belongs to the attack behavior category; when F(Y) ≤ 0.5, it is judged that the data Y does not belong to the attack behavior category.

7. The cloud computing-based smart grid substation management method according to claim 6, characterized in that: The step of immediately activating the corresponding response mechanism and at the same time conducting visual display through the enterprise power operation and maintenance cloud platform once an attack behavior is identified is specifically as follows: once an attack behavior is identified, the power grid substation immediately activates the corresponding response mechanism, including automatically isolating the affected network, isolating faulty equipment, adjusting load distribution, sending alarm notifications, recording events and generating reports, starting emergency plans, implementing defense measures, and coordinating responses; automatically notify the operation and maintenance personnel to take measures according to the type and severity of the attack and record the operations; all data and time records are visually displayed through the enterprise power operation and maintenance platform; Operation and maintenance personnel can check the operating status of the power grid system through the operation and maintenance platform.

8. A cloud computing-based smart grid substation management system, based on the cloud computing-based smart grid substation management method according to any one of claims 1 to 7, characterized in that: Including, collection module, upload module, credibility module, identification and classification module, response record module; The acquisition module is used to collect power data through various sensors and intelligent devices installed in the smart grid substation and perform data preprocessing on the edge computing node; The credibility module is used to upload the pre-processed data to the cloud computing platform and use the Bayesian algorithm to perform credibility analysis on the data; The identification and classification module is used to identify and classify attack behaviors using a support vector machine (SVM) model combined with a kernel function for data that has passed credibility verification; The response recording module is used to immediately initiate a corresponding response mechanism once an attack behavior is identified, and to perform a visual display through the enterprise power operation and maintenance cloud platform.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the cloud computing-based smart grid substation management method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cloud computing-based smart grid substation management method according to any one of claims 1 to 7 are implemented.

Images